Related papers: Evaluating the Impact of Source Code Parsers on ML…
Large Language Models (LLMs) have emerged as coding assistants, capable of generating source code from natural language prompts. With the increasing adoption of LLMs in software development, academic research and industry based projects are…
Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come…
Recent advancements in developing Pre-trained Language Models for Code (Code-PLMs) have urged many areas of Software Engineering (SE) and brought breakthrough results for many SE tasks. Though these models have achieved the state-of-the-art…
Large language models are increasingly becoming a popular tool for software development. Their ability to model and generate source code has been demonstrated in a variety of contexts, including code completion, summarization, translation,…
A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems.…
Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly…
Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (DSLs) remains underexplored, especially for repository-scale change generation spanning…
While large language models (LLMs) have demonstrated remarkable performance on high-level semantic tasks, they often struggle with fine-grained, token-level understanding and structural reasoning--capabilities that are essential for…
Understanding and reasoning about code semantics is essential for enhancing code LLMs' abilities to solve real-world software engineering (SE) tasks. Although several code reasoning benchmarks exist, most rely on synthetic datasets or…
In this work we systematically review the recent advancements in software engineering with language models, covering 70+ models, 40+ evaluation tasks, 180+ datasets, and 900 related works. Unlike previous works, we integrate software…
Existing datasets for coding agents evaluate performance on isolated, single pull request (PR) tasks in a stateless manner, failing to capture the reality of real-world software development where code changes accumulate, technical debt…
Software engineers in various industrial domains are already using Large Language Models (LLMs) to accelerate the process of implementing parts of software systems. When considering its potential use for ADAS or AD systems in the automotive…
Code smells are symptoms of potential code quality problems that may affect software maintainability, thus increasing development costs and impacting software reliability. Large language models (LLMs) have shown remarkable capabilities for…
Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…
Code quality is an attribute composed of various metrics, such as complexity, readability, testability, interoperability, reusability, and the use of good or bad practices, among others. Static code analysis tools aim to measure a set of…
Design patterns provide reusable solutions to recurring software design problems. Automatically detecting these patterns in source code can help bootstrap new developers' understanding of unfamiliar software system architectures, and can…
Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…
Multilingual programming, which involves using multiple programming languages (PLs) in a single project, is increasingly common due to its benefits. However, it introduces cross-language bugs (CLBs), which arise from interactions between…
Recently there have been many advances in research on language modeling of source code. Applications range from code suggestion and completion to code summarization. However, complete program synthesis of industry-grade programming…
Existing code generation benchmarks for Large Language Models (LLMs) such as HumanEval and MBPP are designed to study LLMs' end-to-end performance, where the benchmarks feed a problem description in natural language as input and examine the…